system

Abstract

We provide the system. [Solution] A computation means that receives user information and generates an individualized training plan, An analysis means that receives a real-time video stream from a terminal and performs video analysis, A feedback generation means generates feedback regarding the user's action form based on the analysis results and sends it to the terminal, A data management system that saves the user's training history and reflects it in the next training plan, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional gym, there is a problem that it is difficult to provide individual training guidance to users if a personal trainer is not physically present. Also, when the schedules of the trainer and the user do not match, the continuity of personal training may be impaired. Furthermore, it has been difficult to maintain the consistency of guidance when moving to a distant location. As a result, there is a problem that it cannot meet the modern need to continue fitness flexibly at any time and anywhere.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a system comprising: a calculation means for receiving user information and generating an individualized training plan; an analysis means for receiving a real-time video stream from a terminal and performing video analysis; a feedback generation means for generating feedback on the user's movement form based on the analysis results and sending it to the terminal; and a data management means for saving the user's training history and reflecting it in the next training plan. With this system, users can receive individualized training guidance without being restricted by time or location.

[0006] "User information" refers to the user's personal data and information about their fitness goals, and is the basis for customizing training programs.

[0007] A "training plan" refers to a specific plan of exercises and activities designed based on the user's fitness goals.

[0008] "Computational means" refers to a function that uses a computer to process user information and generate individual training plans.

[0009] "Real-time video streaming" refers to a technology that transmits video captured by a device's camera to a server or other location without delay.

[0010] "Analysis means" refers to technology that receives real-time video streams and performs analysis to understand movement form and actions.

[0011] "Feedback generation means" refers to a system function that determines areas for improvement and points to note based on the user's actions and notifies the user.

[0012] "Data management means" refers to a system for securely and efficiently recording and managing users' training history and account information. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The system of the present invention provides an individualized personal training environment by implementing the following main functions.

[0035] First, users create an account and complete initial setup using a mobile app or web application. Here, users enter personal information such as their name, age, gender, exercise experience, and fitness goals. The device collects this information and sends it to the server.

[0036] Based on the received user information, the server uses AI to automatically generate a training plan tailored to that user. This plan is customized to the user's training goals and includes details such as the type of exercise, number of repetitions, frequency, and intensity.

[0037] When starting a training session, the user launches the app and selects "Start Training," using their device's camera to send a real-time video stream to the server. The server receives this video stream and uses AI and image analysis technology to evaluate the user's form and movements. The analyzed data is instantly generated as feedback, providing instructions to help the user improve their form. This feedback is sent to the device via voice and text messages, and the user adjusts their training based on it.

[0038] At the end of a training session, the user selects "End Training" in the app. This sends the session data back to the server, where it is stored in the user's training history using data management tools. This history information is used to customize the next training session, allowing for adjustments to the plan based on the user's progress.

[0039] For example, if a user is performing squats, the server analyzes the user's posture in real time and provides feedback such as "You need to bend your knees more" or "Keep your torso straight," offering immediately actionable advice. In this way, users can improve the quality of their training based on the feedback, even on their own, and obtain an optimized fitness experience.

[0040] This system allows users to receive personalized training guidance anytime, anywhere.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user launches the app and enters information to create an account. The device retrieves this information and sends the user data along with their fitness goals to the server.

[0044] Step 2:

[0045] The server analyzes the received user information and uses an AI model to automatically generate an initial training plan based on the user's fitness level and goals. The training plan includes recommended exercises, sets, repetitions, and rest times.

[0046] Step 3:

[0047] When a user begins training, they press the "Start Training" button on their device. The device activates its camera and sends a real-time video stream of the user's movements to the server.

[0048] Step 4:

[0049] The server receives the video stream in real time and uses AI and image analysis technology to analyze the user's form and movements. It detects key points in the skeleton and posture, and evaluates whether the form is correct.

[0050] Step 5:

[0051] Based on the analysis results, the server generates feedback on the user's form. This feedback is generated in both audio and text formats and includes specific suggestions for improvement and points to note.

[0052] Step 6:

[0053] Depending on the device, feedback is displayed to the user in real time, and voice guidance prompts adjustments to their movements. The user uses this as a reference to correct their posture and movements.

[0054] Step 7:

[0055] When a user finishes training, they press the "End Training" button. The device then sends the session data to the server.

[0056] Step 8:

[0057] The server saves the received session data to the user's training history and uses it to adjust and update future training plans. This enables continuous fitness improvement.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] Conventional training support systems struggle to provide personalized exercise plans that meet the individual needs of each user, and they also lack sufficient real-time feedback and confirmation of movement form. As a result, users miss opportunities to learn optimal exercise methods, leading to a challenge in achieving effective training.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes a calculation means for receiving basic user information and generating an individualized exercise plan, an analysis means for receiving a real-time video stream from a terminal and performing image analysis, and a feedback generation means for generating immediate feedback on the user's exercise form based on the analysis results and transmitting it to the terminal. This makes it possible to provide training support tailored to the user's individual exercise needs and an optimal exercise experience through immediate and accurate movement evaluation.

[0063] "User basic information" refers to personal attribute data, including name, age, gender, exercise experience, and fitness goals, which users provide when registering for the application.

[0064] A "personalized exercise plan" is a training schedule that customizes the type, number of repetitions, frequency, and intensity of exercises based on each user's basic information and exercise history.

[0065] "Computational means" refers to the collective set of logical components and algorithms used to process user information within a server and generate personalized movement plans.

[0066] A "real-time video stream" is a continuous stream of video data transmitted from a terminal and transferred to a server with virtually no time delay.

[0067] "Image analysis" is a process in which a server recognizes the user's posture and movements from video data it receives and performs structural analysis.

[0068] A "feedback generation means" is a logical configuration and system that generates information pointing out areas for improvement in exercise form to the user based on the results of image analysis and transmits it to the terminal.

[0069] "Data management methods" refer to database operation techniques for systematically storing and managing users' exercise history and feedback history, and reflecting this information in future exercise plans.

[0070] A "generative AI model" is a general term for learning algorithms and models that use artificial intelligence technology to generate optimal movement plans based on user information.

[0071] A "structure detection algorithm" refers to numerical methods or mathematical calculations used to analyze the position and movement of various parts of a user's body.

[0072] This invention is a system designed to provide users with a personalized training experience. This system primarily utilizes servers, terminals, and AI technology to build a personalized exercise plan based on the user's basic information and to evaluate exercise form in real time.

[0073] First, the user accesses a dedicated application using a mobile device or computer. Here, the user enters basic information such as name, age, gender, exercise experience, and fitness goals. This information is collected on the device and transmitted to the server via Universal Networking.

[0074] The server processes the received user information and automatically generates a personalized exercise plan using a generative AI model. This plan includes the type, number of repetitions, frequency, and intensity of exercise, and is optimized to help the user achieve their goals. The AI ​​technology utilizes existing learning models and algorithms to select a plan that has a high degree of fit with the user's personal data.

[0075] When a user begins training, the device activates its built-in camera and sends the user's movements as a video stream to the server. The server analyzes this video in real time and uses image analysis technology to evaluate the user's exercise form. A specific structure detection algorithm is used in the analysis to determine how well the user's posture and movements match standard form.

[0076] Based on the analysis results, the server generates feedback on the user's exercise form, including areas for improvement and advice, and sends it to the device. The feedback is immediate and displayed on the device as voice messages or text, allowing the user to adjust their form in real time.

[0077] As a concrete example, consider a scenario where a user is performing squats. The server monitors the user's posture and provides specific feedback on knee flexion and core stability. Instructions such as "Don't let your knees go forward a little more" are communicated to the user via voice or text.

[0078] An example of a prompt message would be, "Analyze the user's squat training video and provide correct form and areas for improvement." This allows the user to continue high-quality training while making self-improvements.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] Users access a dedicated application using their device and enter basic information such as their name, age, gender, exercise experience, and fitness goals. The entered information is collected as a dataset by the device and sent to the server. The server receives this data, stores it in a database, and uses it as input for the next processing step.

[0082] Step 2:

[0083] The server uses an AI model based on the user's basic information to generate a personalized exercise plan. User information is fed into the AI ​​algorithm, and through computational processing, an exercise plan is generated that proposes the optimal type, number of repetitions, frequency, and intensity of exercise. The exercise plan is stored in a database and sent to the user's terminal.

[0084] Step 3:

[0085] The user selects the "Start Training" button on the device to begin training. The device activates its camera and transmits the user's training as a real-time video stream to the server. During this process, the user's movement data is sent to the server as input.

[0086] Step 4:

[0087] The server analyzes the acquired video stream and uses image analysis technology to evaluate the user's movement form. Based on the input video data, a structure detection algorithm analyzes the user's posture and movements and evaluates the accuracy of the form. As a result of the analysis, the system identifies points that need correction.

[0088] Step 5:

[0089] Based on the analysis results, the server generates immediate feedback about the user's exercise form. It converts the analysis results, as input, into prompts, creating specific instructions such as "bend your knees a little more" as feedback. This feedback is then sent to the terminal.

[0090] Step 6:

[0091] The user receives feedback displayed on their device, along with warnings and advice in audio or text format. Based on this feedback, the user attempts to improve their form and movements, and adjusts their training accordingly. By accepting the feedback, the training effect can be immediately improved.

[0092] Step 7:

[0093] After completing the training session, the user presses the "End Training" button to end the session. The device sends the exercise data and feedback history collected during the session to the server, where it is stored in a database by a data management system. This history is used to optimize the next exercise plan.

[0094] (Application Example 1)

[0095] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] Improving worker efficiency and safety in factory operations is a challenge. Traditional work instruction is limited to general guidance, making it difficult to provide efficient, individualized feedback tailored to each worker.

[0097] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0098] In this invention, the server includes a computing means for receiving user information and generating an individualized training plan, an analysis means for receiving a real-time video stream from a terminal and performing video analysis, and a means for analyzing the worker's movements based on the analysis results and providing feedback on efficient work methods. This enables optimal movement guidance for individual workers and improved safety.

[0099] "User information" refers to basic data related to the user that is collected in order to generate a personalized training plan.

[0100] A "training plan" refers to a set of exercise and work instructions customized to a specific user's abilities and goals.

[0101] "Calculation means" refers to a device or system that performs calculations to create a customized plan based on user information.

[0102] A "real-time video stream" refers to video data that is transmitted from a terminal to a server and flows continuously without any time delay.

[0103] "Analysis means for performing video analysis" refers to a device or process for extracting meaningful information from real-time video and evaluating user movements.

[0104] "Feedback generation means" refers to a device or program that generates suggestions for improvement and effective work methods to show the user based on the analyzed data.

[0105] "Data management means" refers to a system that stores user account information, training history, and feedback history, and uses this information to inform future plans.

[0106] "Means for analyzing worker movements and providing feedback on efficient work methods" refers to devices or methods that analyze worker movements and provide guidance to improve work safety and efficiency.

[0107] The system of this invention mainly consists of three elements: a server, a terminal, and a user. The server receives user information and generates a personalized training plan using AI technology. This AI technology is implemented using a widely used deep learning library such as TENSORFLOW®. The generated training plan provides detailed guidance, including the type, frequency, and intensity of exercise or work.

[0108] The terminal refers to devices such as smartphones and tablets, which are the primary devices operated by the user. This terminal transmits camera footage to a server in real time, capturing the user's movements. The video data is processed by analysis tools to evaluate whether the user's movement form is correct. Image processing libraries such as OpenCV are commonly used for this analysis.

[0109] The user receives feedback through their device. The feedback generation system presents the feedback, created based on the analysis results, to the user as text or voice messages. This feedback allows the user to immediately review their actions and make improvements.

[0110] For example, when a worker operates a robotic arm in a factory, the system provides specific advice such as, "You need to tilt the robotic arm more to the right." This advice improves work efficiency and enhances safety.

[0111] An example of a prompt to input into the generating AI model is, "Please consider what kind of action improvement advice is needed for the worker to perform their duties safely." This prompt can improve the accuracy of the feedback generated by the AI.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The terminal is powered on, and the user logs into the application. The user enters personal information such as name, age, and exercise experience, and sends it to the server. The entered information is stored on the server as user information.

[0115] Step 2:

[0116] The server uses AI technology to generate a personalized training plan based on the received user information. Using libraries such as TensorFlow, the optimal type, frequency, and intensity of exercise for this user are calculated. The generated training plan is stored in a database and sent to the terminal.

[0117] Step 3:

[0118] When a user begins training, the device's camera is activated, and a real-time video stream is sent to the server. This video captures the worker's movements and is used as data for analysis. Skeletal detection is performed using OpenCV, and the movement form is evaluated.

[0119] Step 4:

[0120] The server generates feedback on the user's actions based on the analysis results. If the user's form is inappropriate, it identifies areas for improvement and creates instructions to convey to the user through the feedback generation mechanism. For example, if the action is insufficient, text feedback such as "You need to bend your knees more" is generated.

[0121] Step 5:

[0122] Feedback is displayed on the user's device as text or voice messages. The user uses this feedback to adjust their actions and strive to perform appropriate actions. This improves operational efficiency and safety.

[0123] Step 6:

[0124] After a training session ends, session data is sent from the user's device to the server. The server receives this data and saves it as the user's training history using a data management system. This saved history is then used to generate the next training plan.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] The system of this invention is designed to provide users with personalized fitness and training guidance and feedback that takes into account the user's emotions. The system is configured as follows:

[0127] First, users create an account via a mobile or web application and enter their personal information and fitness goals. The device sends this information to a server. The server uses AI technology to generate and propose a personalized training plan tailored to the user's needs.

[0128] During training, the device captures the user's video in real time and sends the video stream to the server. Upon receiving the video data, the server uses image analysis technology to analyze the skeletal structure and movements. The analyzed data is used to evaluate the user's movement form and generate specific feedback.

[0129] Furthermore, the system incorporates an emotion engine, allowing the server to analyze the user's emotions from their facial expressions and behavior. This analysis measures the user's motivation and stress levels, enabling the system to adjust feedback and training content accordingly. For example, if a user is tired, the system might recommend relaxing stretches rather than strenuous exercise.

[0130] Furthermore, based on the user's emotional state, the server generates and sends positive, personalized coaching messages to the user's device. These messages take into account the user's psychological state and support their motivation for training. For example, if the server detects that the user is feeling discouraged, it will provide encouraging messages such as, "Your efforts are paying off; by continuing, you will get closer to your goal."

[0131] At the end of a training session, the user saves all data using the session end button and sends it to the server. This data is stored for long-term performance improvement and used to adjust future plans.

[0132] This system allows users to receive training tailored to their physical and emotional needs, resulting in more consistent motivation and more effective fitness improvements.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The user launches the app and enters the necessary personal information and fitness goals to create an account. The device then sends this information to the server.

[0136] Step 2:

[0137] The server analyzes the received user information and uses AI technology to generate a personalized training plan. The training plan includes specific exercises based on the user's exercise experience and goals.

[0138] Step 3:

[0139] When a user begins training, the device's camera is activated, and the user's video is sent to the server in real time. The device captures and transmits the video data.

[0140] Step 4:

[0141] The server uses skeletal detection and motion analysis algorithms to evaluate the user's movement form in order to analyze the received real-time video.

[0142] Step 5:

[0143] Based on the analysis results, the server generates feedback for improving forms and performance, and sends this feedback to the device. This feedback is notified to the user via voice or text.

[0144] Step 6:

[0145] The server further analyzes the user's facial expressions from the video data and uses an emotion engine to evaluate the user's emotional state. This emotion data is used to adjust the difficulty level of the training.

[0146] Step 7:

[0147] The device provides users with feedback and motivational messages that reflect their emotional state. This allows users to receive appropriate guidance based on their emotions.

[0148] Step 8:

[0149] After the training session ends, the user presses the "End Training" button on their device to send the session data to the server. The server saves the data and uses it to help plan the next training session.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0152] There are challenges in fitness and training, such as the difficulty users receive guidance that takes into account their individual physical condition and emotional state, making it difficult to achieve results with general plans. Furthermore, the lack of real-time feedback and long-term data utilization makes it difficult for users to maintain their motivation.

[0153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0154] In this invention, the server includes a computation means for receiving user information and generating an individualized exercise plan using a generated artificial intelligence model; an analysis means for receiving a real-time image data stream and performing video analysis; and an emotion analysis means for analyzing the user's emotions and reflecting them in the movement plan and feedback. This makes it possible to provide personalized training that takes into account not only the user's physical condition but also their emotional state.

[0155] "User information" refers to personal data provided by the user, including name, age, gender, and fitness goals.

[0156] A "generative artificial intelligence model" is a technology that uses machine learning algorithms to analyze movement patterns and emotions, and then generates personalized motor plans.

[0157] An "exercise plan" is a specific schedule or guideline of fitness and training activities tailored to the individual user's physical and emotional condition.

[0158] "Computation means" refers to a computer system or its components for processing user information and generating personalized movement plans.

[0159] A "real-time image data stream" is a continuous stream of video data sent from a terminal to a server to record user activity.

[0160] "Video analysis" is a process that uses image analysis technology to analyze and evaluate user behavior from received video data.

[0161] "Analysis means" refers to a device or program equipped with image analysis technology for the purpose of processing video data and analyzing the user's behavior patterns.

[0162] "Motion style" refers to the structure and arrangement of the user's physical movements and poses.

[0163] A "feedback generation means" is a system that has the function of generating guidance and improvement suggestions regarding the user's actions based on the analyzed data and sending them to the terminal.

[0164] "Emotional analysis" is a process that evaluates a user's emotional state based on their facial expressions and behavior, and measures their motivation, stress levels, and other factors.

[0165] An "emotion analysis tool" is a system or program that processes facial expression and behavioral data in order to analyze a user's emotions.

[0166] "Information management means" refers to a system that organizes, stores, and manages users' training history, feedback history, and account information.

[0167] The system of this invention provides personalized fitness and training guidance that also takes emotional aspects into consideration. This system is configured as follows:

[0168] First, users enter their personal information and fitness goals using a mobile or web-based device. This information is transmitted to a server via the internet. The server uses a generative AI model to generate a personalized exercise plan based on the user's information. This model is built using machine learning algorithms and develops new plans based on the latest training data and past user history.

[0169] When a user begins training, the device uses its built-in camera to capture the user's movements in real time and streams the video data to the server. The server then uses image analysis technology to analyze the received video data and the user's movements. This analysis, which utilizes open pose and deep learning, evaluates the user's skeletal structure and movement patterns, and generates feedback.

[0170] Furthermore, the system incorporates an emotion analysis engine. The server receives the user's facial expression data and analyzes their emotional state. Based on this analysis, it evaluates the user's motivation and stress level and adjusts the training content by providing appropriate feedback. For example, it might suggest relaxing stretches to a tired user, or send a message to a user feeling discouraged, such as "Your efforts are paying off; continuing will bring you closer to your goal."

[0171] After a training session ends, the user presses the "End Session" button to send all session data to the server. This transmitted data is stored as a long-term fitness history and used to adjust future exercise plans.

[0172] As a concrete example, here is an example of a prompt statement for a generative AI model that issues instructions to the system:

[0173] "Based on the user's fitness data and emotional state, suggest a training plan for their next session."

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] Users open the fitness app on their device, create an account, and enter their personal information and fitness goals. This information is sent to the server via the device. The entered data is stored in a database on the server and serves as the basis for generating personalized exercise plans.

[0177] Step 2:

[0178] The server receives the user's personal information and goal data, and then uses a generative AI model to create a personalized exercise plan. Input data includes age, gender, fitness level, and goals (e.g., weight loss, muscle gain). The server processes this data and uses a machine learning algorithm to calculate the optimal exercise plan. The generated exercise plan is sent to the user's device and displayed within the app.

[0179] Step 3:

[0180] When a user begins exercising, the device uses its built-in camera to capture real-time video of the user. This video data is streamed to a server. The server analyzes the received video and uses image analysis technology to analyze the user's movements. The input data is a video stream, and the accuracy and efficiency of the movements are evaluated based on this. Useful feedback is returned to the device.

[0181] Step 4:

[0182] The server generates specific feedback for the user based on the analyzed motion data. From the results obtained from the analysis (e.g., posture, motion accuracy), it identifies areas for improvement in the user's movements and creates advice based on those areas. The generated feedback is sent to the terminal, allowing the user to view it in real time.

[0183] Step 5:

[0184] During training, the server performs emotion analysis by receiving data from the user's facial expressions. The input includes videos of the user, which the server analyzes to measure the user's motivation and stress level. Based on the emotion analysis results, the training content and feedback are adjusted in real time. For example, if the server determines that the user is tired, a suggestion to reduce the intensity of the exercise will be added as feedback.

[0185] Step 6:

[0186] After completing a training session, the user presses the "End Session" button to send the entire session data to the server. This data (movement data, execution status of the exercise plan, and feedback history) is stored on the server and used to adjust future training plans. It is also accumulated in a database as long-term fitness history and used when creating the next plan.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0189] The goal is to provide a system that offers personalized fitness instruction that considers not only the user's movement patterns but also their psychological state when providing feedback. Such a system is expected to make the user's training experience more effective and motivating.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0191] In this invention, the server includes a computing device that receives user information and generates an individualized training plan; an analysis device that receives a real-time video data stream from a terminal and performs video analysis; a feedback generation device that generates feedback regarding the user's movement patterns based on the analysis results and transmits it to the terminal; and an emotion analysis device that detects the user's emotional state and adaptively adjusts the training content accordingly. This enables fitness instruction that is tailored to the user's physical and emotional needs.

[0192] "User information" refers to data that can identify a user, including information such as fitness goals and individual physical characteristics.

[0193] A "training plan" is an exercise program tailored to the user's goals and fitness level.

[0194] A "computational device" is an electronic device used to process user information and generate an optimal training plan.

[0195] A "terminal" is a device used by a user that has the means to communicate with the system.

[0196] A "video data stream" is a continuous stream of image data that records the user's movements and actions in real time.

[0197] An "analysis device" is a device that analyzes received video data and evaluates the user's behavior.

[0198] A "feedback generation device" is a device that provides accurate advice and guidance to the user based on the results obtained from an analysis device.

[0199] An "information management device" is a device that stores and manages a user's training history and other related information.

[0200] An "emotion analysis device" is a device that determines a user's emotions from their facial expressions and behavior and reflects that in their fitness program.

[0201] This system is comprised of various technological elements combined to provide personalized fitness instruction. Users first create an account using a terminal and input their fitness goals and personal information. The terminal sends this information to a server, which uses a computing device to generate a personalized training plan for the user.

[0202] During training, the device captures the user's movements and sends them to the server as a video data stream. The server's analysis system uses image analysis libraries such as OpenCV to analyze the user's skeletal structure and movements in the video in real time. At the same time, an emotion analysis system is also running, using software such as EmotionEngine to extract emotions from the user's facial expressions.

[0203] Based on the analysis results, the server's feedback generator produces and sends to the user advice on movement patterns and psychological support messages to the terminal. The feedback is adaptively adjusted to the user's movement patterns and emotional state. This allows the user to continue receiving appropriate guidance throughout the training.

[0204] For example, if a user shows signs of discouragement during training, the server will send a message such as, "Your efforts are paying off, keep going a little longer!"

[0205] An example of a prompt message could be an instruction given to a generating AI model: "Analyze user behavior in real time and provide appropriate guidance."

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The user creates an account using their device and enters their fitness goals and personal information. The entered information is sent from the device to the server. The server receives this information and stores it in its database. Here, the input is user information, and the output is the information stored on the server.

[0209] Step 2:

[0210] The server uses computing power to process received user information and generate a personalized training plan. An AI algorithm designs the plan based on the user's goals and fitness level. The input at this stage is stored user information, and the output is a personalized training plan.

[0211] Step 3:

[0212] During training, the user uses a device to record their movements. The device sends a video data stream to the server in real time. The input is the video data of the user during training, and the output is the real-time video stream sent to the server.

[0213] Step 4:

[0214] The server's analysis device receives video data using image analysis libraries such as OpenCV and analyzes the user's skeleton and movements. It extracts coordinates from the image data and evaluates the accuracy of the movements. The input is a real-time video stream, and the output is analyzed movement data.

[0215] Step 5:

[0216] The analysis device uses EmotionEngine to extract emotions from the user's face. This converts the user's psychological state into data. The input is the user's facial expression data, and the output is numerical data of their emotional state.

[0217] Step 6:

[0218] The server's feedback generator produces feedback based on behavioral and emotional data. This is where suggested form revisions based on the analysis results and messages aimed at improving motivation are created. The input is behavioral and emotional data, and the output is a feedback message for the user.

[0219] Step 7:

[0220] The generated feedback is sent to the device and displayed to the user. The user can then adjust the training content based on this feedback. The input is the generated feedback message, and the output is what is displayed on the user's device.

[0221] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0222] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0223] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0227] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0228] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0229] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0230] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0231] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0232] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0233] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0234] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0235] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0236] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0237] The system of the present invention provides an individualized personal training environment by implementing the following main functions.

[0238] First, users create an account and complete initial setup using a mobile app or web application. Here, users enter personal information such as their name, age, gender, exercise experience, and fitness goals. The device collects this information and sends it to the server.

[0239] Based on the received user information, the server uses AI to automatically generate a training plan tailored to that user. This plan is customized to the user's training goals and includes details such as the type of exercise, number of repetitions, frequency, and intensity.

[0240] When starting a training session, the user launches the app and selects "Start Training," using their device's camera to send a real-time video stream to the server. The server receives this video stream and uses AI and image analysis technology to evaluate the user's form and movements. The analyzed data is instantly generated as feedback, providing instructions to help the user improve their form. This feedback is sent to the device via voice and text messages, and the user adjusts their training based on it.

[0241] At the end of a training session, the user selects "End Training" in the app. This sends the session data back to the server, where it is stored in the user's training history using data management tools. This history information is used to customize the next training session, allowing for adjustments to the plan based on the user's progress.

[0242] For example, if a user is performing squats, the server analyzes the user's posture in real time and provides feedback such as "You need to bend your knees more" or "Keep your torso straight," offering immediately actionable advice. In this way, users can improve the quality of their training based on the feedback, even on their own, and obtain an optimized fitness experience.

[0243] This system allows users to receive personalized training guidance anytime, anywhere.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The user launches the app and enters information to create an account. The device retrieves this information and sends the user data along with their fitness goals to the server.

[0247] Step 2:

[0248] The server analyzes the received user information and uses an AI model to automatically generate an initial training plan based on the user's fitness level and goals. The training plan includes recommended exercises, sets, repetitions, and rest times.

[0249] Step 3:

[0250] When a user begins training, they press the "Start Training" button on their device. The device activates its camera and sends a real-time video stream of the user's movements to the server.

[0251] Step 4:

[0252] The server receives the video stream in real time and uses AI and image analysis technology to analyze the user's form and movements. It detects key points in the skeleton and posture, and evaluates whether the form is correct.

[0253] Step 5:

[0254] Based on the analysis results, the server generates feedback on the user's form. This feedback is generated in both audio and text formats and includes specific suggestions for improvement and points to note.

[0255] Step 6:

[0256] Depending on the device, feedback is displayed to the user in real time, and voice guidance prompts adjustments to their movements. The user uses this as a reference to correct their posture and movements.

[0257] Step 7:

[0258] When a user finishes training, they press the "End Training" button. The device then sends the session data to the server.

[0259] Step 8:

[0260] The server saves the received session data to the user's training history and uses it to adjust and update future training plans. This enables continuous fitness improvement.

[0261] (Example 1)

[0262] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0263] Conventional training support systems struggle to provide personalized exercise plans that meet the individual needs of each user, and they also lack sufficient real-time feedback and confirmation of movement form. As a result, users miss opportunities to learn optimal exercise methods, leading to a challenge in achieving effective training.

[0264] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0265] In this invention, the server includes a calculation means for receiving basic user information and generating an individualized exercise plan, an analysis means for receiving a real-time video stream from a terminal and performing image analysis, and a feedback generation means for generating immediate feedback on the user's exercise form based on the analysis results and transmitting it to the terminal. This makes it possible to provide training support tailored to the user's individual exercise needs and an optimal exercise experience through immediate and accurate movement evaluation.

[0266] "User basic information" refers to personal attribute data, including name, age, gender, exercise experience, and fitness goals, which users provide when registering for the application.

[0267] A "personalized exercise plan" is a training schedule that customizes the type, number of repetitions, frequency, and intensity of exercises based on each user's basic information and exercise history.

[0268] "Computational means" refers to the collective set of logical components and algorithms used to process user information within a server and generate personalized movement plans.

[0269] A "real-time video stream" is a continuous stream of video data transmitted from a terminal and transferred to a server with virtually no time delay.

[0270] "Image analysis" is a process in which a server recognizes the user's posture and movements from video data it receives and performs structural analysis.

[0271] A "feedback generation means" is a logical configuration and system that generates information pointing out areas for improvement in exercise form to the user based on the results of image analysis and transmits it to the terminal.

[0272] "Data management methods" refer to database operation techniques for systematically storing and managing users' exercise history and feedback history, and reflecting this information in future exercise plans.

[0273] A "generative AI model" is a general term for learning algorithms and models that use artificial intelligence technology to generate optimal movement plans based on user information.

[0274] A "structure detection algorithm" refers to numerical methods or mathematical calculations used to analyze the position and movement of various parts of a user's body.

[0275] This invention is a system designed to provide users with a personalized training experience. This system primarily utilizes servers, terminals, and AI technology to build a personalized exercise plan based on the user's basic information and to evaluate exercise form in real time.

[0276] First, the user accesses a dedicated application using a mobile device or computer. Here, the user enters basic information such as name, age, gender, exercise experience, and fitness goals. This information is collected on the device and transmitted to the server via Universal Networking.

[0277] The server processes the received user information and automatically generates a personalized exercise plan using a generative AI model. This plan includes the type, number of repetitions, frequency, and intensity of exercise, and is optimized to help the user achieve their goals. The AI ​​technology utilizes existing learning models and algorithms to select a plan that has a high degree of fit with the user's personal data.

[0278] When a user begins training, the device activates its built-in camera and sends the user's movements as a video stream to the server. The server analyzes this video in real time and uses image analysis technology to evaluate the user's exercise form. A specific structure detection algorithm is used in the analysis to determine how well the user's posture and movements match standard form.

[0279] Based on the analysis results, the server generates feedback on the user's exercise form, including areas for improvement and advice, and sends it to the device. The feedback is immediate and displayed on the device as voice messages or text, allowing the user to adjust their form in real time.

[0280] As a specific example, consider the case where the user is performing a squat. The server checks the user's posture and provides specific feedback regarding the degree of knee bend and the stability of the torso. Instructions such as "Don't extend your knees too far forward" are conveyed to the user in the form of voice or text.

[0281] Examples of prompt sentences include "Analyze the video of the user's squat training and provide correct form and areas for improvement." This enables the user to continue high-quality training while seeking self-improvement.

[0282] The flow of the specific process in Example 1 will be described using FIG. 11.

[0283] Step 1:

[0284] The user uses the terminal to access a dedicated application and enters basic information such as name, age, gender, exercise experience, and fitness goals. The entered information is collected as a dataset by the terminal and transmitted to the server. The server receives this data, stores it in the database, and uses it as input for the next processing step.

[0285] Step 2:

[0286] <f The server utilizes the generated AI model based on the received basic information of the user to generate an individualized exercise plan. The input user information is supplied to the AI algorithm, and through computational processing, an exercise plan is generated that proposes the optimal type, number, frequency, and intensity of exercises. The exercise plan as output is saved in the database and transmitted to the user's terminal.

[0287] Step 3:

[0288] The user selects the "Start Training" button on the terminal to start training. The terminal activates the camera and transfers the user's training situation as a real-time video stream to the server. At this time, the user's motion data is sent to the server as input.

[0289] Step 4:

[0290] The server analyzes the acquired video stream and uses image analysis technology to evaluate the user's movement form. Based on the input video data, a structure detection algorithm analyzes the user's posture and movements and evaluates the accuracy of the form. As a result of the analysis, the system identifies points that need correction.

[0291] Step 5:

[0292] Based on the analysis results, the server generates immediate feedback about the user's exercise form. It converts the analysis results, as input, into prompts, creating specific instructions such as "bend your knees a little more" as feedback. This feedback is then sent to the terminal.

[0293] Step 6:

[0294] The user receives feedback displayed on their device, along with warnings and advice in audio or text format. Based on this feedback, the user attempts to improve their form and movements, and adjusts their training accordingly. By accepting the feedback, the training effect can be immediately improved.

[0295] Step 7:

[0296] After completing the training session, the user presses the "End Training" button to end the session. The device sends the exercise data and feedback history collected during the session to the server, where it is stored in a database by a data management system. This history is used to optimize the next exercise plan.

[0297] (Application Example 1)

[0298] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0299] Improving worker efficiency and safety in factory operations is a challenge. Traditional work instruction is limited to general guidance, making it difficult to provide efficient, individualized feedback tailored to each worker.

[0300] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0301] In this invention, the server includes a computing means for receiving user information and generating an individualized training plan, an analysis means for receiving a real-time video stream from a terminal and performing video analysis, and a means for analyzing the worker's movements based on the analysis results and providing feedback on efficient work methods. This enables optimal movement guidance for individual workers and improved safety.

[0302] "User information" refers to basic data related to the user that is collected in order to generate a personalized training plan.

[0303] A "training plan" refers to a set of exercise and work instructions customized to a specific user's abilities and goals.

[0304] "Calculation means" refers to a device or system that performs calculations to create a customized plan based on user information.

[0305] A "real-time video stream" refers to video data that is transmitted from a terminal to a server and flows continuously without any time delay.

[0306] "Analysis means for performing video analysis" refers to a device or process for extracting meaningful information from real-time video and evaluating user movements.

[0307] The "feedback generation means" refers to a device or program that generates improvement points and effective working methods to be shown to the user based on the analyzed data.

[0308] The "data management means" refers to a system that stores the user's account information, training history, and feedback history and reflects it in the next plan.

[0309] The "means for analyzing the operator's actions and providing feedback on efficient working methods" refers to a device or method that analyzes the operator's actions and provides guidance for improving work safety and efficiency.

[0310] The system of the present invention mainly consists of three elements: a server, a terminal, and a user. The server receives user information and generates an individualized training plan using AI technology. This AI technology is realized by using widely used deep learning libraries such as TensorFlow. The generated training plan provides detailed guidelines including the type, frequency, and intensity of exercises or work.

[0311] The terminal corresponds to devices such as smartphones and tablets and is the main device operated by the user. This terminal transmits real-time camera images to the server to capture the user's actions. The video data is processed by the analysis means to evaluate whether the user's movement form is correct. In general, image processing libraries such as OpenCV are used for this analysis.

[0312] The user receives feedback through the terminal. The feedback created by the feedback generation means based on the analysis results is presented to the user as text or voice messages. With this feedback, the user can immediately check their actions and seek improvement.

[0313] For example, when a worker operates a robotic arm in a factory, the system provides specific advice such as, "You need to tilt the robotic arm more to the right." This advice improves work efficiency and enhances safety.

[0314] An example of a prompt to input into the generating AI model is, "Please consider what kind of action improvement advice is needed for the worker to perform their duties safely." This prompt can improve the accuracy of the feedback generated by the AI.

[0315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0316] Step 1:

[0317] The terminal is powered on, and the user logs into the application. The user enters personal information such as name, age, and exercise experience, and sends it to the server. The entered information is stored on the server as user information.

[0318] Step 2:

[0319] The server uses AI technology to generate a personalized training plan based on the received user information. Using libraries such as TensorFlow, the optimal type, frequency, and intensity of exercise for this user are calculated. The generated training plan is stored in a database and sent to the terminal.

[0320] Step 3:

[0321] When a user begins training, the device's camera is activated, and a real-time video stream is sent to the server. This video captures the worker's movements and is used as data for analysis. Skeletal detection is performed using OpenCV, and the movement form is evaluated.

[0322] Step 4:

[0323] The server generates feedback on the user's actions based on the analysis results. If the user's form is inappropriate, it identifies areas for improvement and creates instructions to convey to the user through the feedback generation mechanism. For example, if the action is insufficient, text feedback such as "You need to bend your knees more" is generated.

[0324] Step 5:

[0325] Feedback is displayed on the user's device as text or voice messages. The user uses this feedback to adjust their actions and strive to perform appropriate actions. This improves operational efficiency and safety.

[0326] Step 6:

[0327] After a training session ends, session data is sent from the user's device to the server. The server receives this data and saves it as the user's training history using a data management system. This saved history is then used to generate the next training plan.

[0328] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0329] The system of this invention is designed to provide users with personalized fitness and training guidance and feedback that takes into account the user's emotions. The system is configured as follows:

[0330] First, users create an account via a mobile or web application and enter their personal information and fitness goals. The device sends this information to a server. The server uses AI technology to generate and propose a personalized training plan tailored to the user's needs.

[0331] During training, the device captures the user's video in real time and sends the video stream to the server. Upon receiving the video data, the server uses image analysis technology to analyze the skeletal structure and movements. The analyzed data is used to evaluate the user's movement form and generate specific feedback.

[0332] Furthermore, the system incorporates an emotion engine, allowing the server to analyze the user's emotions from their facial expressions and behavior. This analysis measures the user's motivation and stress levels, enabling the system to adjust feedback and training content accordingly. For example, if a user is tired, the system might recommend relaxing stretches rather than strenuous exercise.

[0333] Furthermore, based on the user's emotional state, the server generates and sends positive, personalized coaching messages to the user's device. These messages take into account the user's psychological state and support their motivation for training. For example, if the server detects that the user is feeling discouraged, it will provide encouraging messages such as, "Your efforts are paying off; by continuing, you will get closer to your goal."

[0334] At the end of a training session, the user saves all data using the session end button and sends it to the server. This data is stored for long-term performance improvement and used to adjust future plans.

[0335] This system allows users to receive training tailored to their physical and emotional needs, resulting in more consistent motivation and more effective fitness improvements.

[0336] The following describes the processing flow.

[0337] Step 1:

[0338] The user launches the app and enters the necessary personal information and fitness goals to create an account. The device then sends this information to the server.

[0339] Step 2:

[0340] The server analyzes the received user information and uses AI technology to generate a personalized training plan. The training plan includes specific exercises based on the user's exercise experience and goals.

[0341] Step 3:

[0342] When a user begins training, the device's camera is activated, and the user's video is sent to the server in real time. The device captures and transmits the video data.

[0343] Step 4:

[0344] The server uses skeletal detection and motion analysis algorithms to evaluate the user's movement form in order to analyze the received real-time video.

[0345] Step 5:

[0346] Based on the analysis results, the server generates feedback for improving forms and performance, and sends this feedback to the device. This feedback is notified to the user via voice or text.

[0347] Step 6:

[0348] The server further analyzes the user's facial expressions from the video data and uses an emotion engine to evaluate the user's emotional state. This emotion data is used to adjust the difficulty level of the training.

[0349] Step 7:

[0350] The device provides users with feedback and motivational messages that reflect their emotional state. This allows users to receive appropriate guidance based on their emotions.

[0351] Step 8:

[0352] After the training session ends, the user presses the "End Training" button on their device to send the session data to the server. The server saves the data and uses it to help plan the next training session.

[0353] (Example 2)

[0354] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0355] There are challenges in fitness and training, such as the difficulty users receive guidance that takes into account their individual physical condition and emotional state, making it difficult to achieve results with general plans. Furthermore, the lack of real-time feedback and long-term data utilization makes it difficult for users to maintain their motivation.

[0356] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0357] In this invention, the server includes a computation means for receiving user information and generating an individualized exercise plan using a generated artificial intelligence model; an analysis means for receiving a real-time image data stream and performing video analysis; and an emotion analysis means for analyzing the user's emotions and reflecting them in the movement plan and feedback. This makes it possible to provide personalized training that takes into account not only the user's physical condition but also their emotional state.

[0358] "User information" refers to personal data provided by the user, including name, age, gender, and fitness goals.

[0359] A "generative artificial intelligence model" is a technology that uses machine learning algorithms to analyze movement patterns and emotions, and then generates personalized motor plans.

[0360] An "exercise plan" is a specific schedule or guideline of fitness and training activities tailored to the individual user's physical and emotional condition.

[0361] "Computation means" refers to a computer system or its components for processing user information and generating personalized movement plans.

[0362] A "real-time image data stream" is a continuous stream of video data sent from a terminal to a server to record user activity.

[0363] "Video analysis" is a process that uses image analysis technology to analyze and evaluate user behavior from received video data.

[0364] "Analysis means" refers to a device or program equipped with image analysis technology for the purpose of processing video data and analyzing the user's behavior patterns.

[0365] "Motion style" refers to the structure and arrangement of the user's physical movements and poses.

[0366] A "feedback generation means" is a system that has the function of generating guidance and improvement suggestions regarding the user's actions based on the analyzed data and sending them to the terminal.

[0367] "Emotional analysis" is a process that evaluates a user's emotional state based on their facial expressions and behavior, and measures their motivation, stress levels, and other factors.

[0368] An "emotion analysis tool" is a system or program that processes facial expression and behavioral data in order to analyze a user's emotions.

[0369] "Information management means" refers to a system that organizes, stores, and manages users' training history, feedback history, and account information.

[0370] The system of this invention provides personalized fitness and training guidance that also takes emotional aspects into consideration. This system is configured as follows:

[0371] First, users enter their personal information and fitness goals using a mobile or web-based device. This information is transmitted to a server via the internet. The server uses a generative AI model to generate a personalized exercise plan based on the user's information. This model is built using machine learning algorithms and develops new plans based on the latest training data and past user history.

[0372] When a user begins training, the device uses its built-in camera to capture the user's movements in real time and streams the video data to the server. The server then uses image analysis technology to analyze the received video data and the user's movements. This analysis, which utilizes open pose and deep learning, evaluates the user's skeletal structure and movement patterns, and generates feedback.

[0373] Furthermore, the system incorporates an emotion analysis engine. The server receives the user's facial expression data and analyzes their emotional state. Based on this analysis, it evaluates the user's motivation and stress level and adjusts the training content by providing appropriate feedback. For example, it might suggest relaxing stretches to a tired user, or send a message to a user feeling discouraged, such as "Your efforts are paying off; continuing will bring you closer to your goal."

[0374] After a training session ends, the user presses the "End Session" button to send all session data to the server. This transmitted data is stored as a long-term fitness history and used to adjust future exercise plans.

[0375] As a concrete example, here is an example of a prompt statement for a generative AI model that issues instructions to the system:

[0376] "Based on the user's fitness data and emotional state, suggest a training plan for their next session."

[0377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0378] Step 1:

[0379] Users open the fitness app on their device, create an account, and enter their personal information and fitness goals. This information is sent to the server via the device. The entered data is stored in a database on the server and serves as the basis for generating personalized exercise plans.

[0380] Step 2:

[0381] The server receives the user's personal information and goal data, and then uses a generative AI model to create a personalized exercise plan. Input data includes age, gender, fitness level, and goals (e.g., weight loss, muscle gain). The server processes this data and uses a machine learning algorithm to calculate the optimal exercise plan. The generated exercise plan is sent to the user's device and displayed within the app.

[0382] Step 3:

[0383] When a user begins exercising, the device uses its built-in camera to capture real-time video of the user. This video data is streamed to a server. The server analyzes the received video and uses image analysis technology to analyze the user's movements. The input data is a video stream, and the accuracy and efficiency of the movements are evaluated based on this. Useful feedback is returned to the device.

[0384] Step 4:

[0385] The server generates specific feedback for the user based on the analyzed motion data. From the results obtained from the analysis (e.g., posture, motion accuracy), it identifies areas for improvement in the user's movements and creates advice based on those areas. The generated feedback is sent to the terminal, allowing the user to view it in real time.

[0386] Step 5:

[0387] During training, the server performs emotion analysis by receiving data from the user's facial expressions. The input includes videos of the user, which the server analyzes to measure the user's motivation and stress level. Based on the emotion analysis results, the training content and feedback are adjusted in real time. For example, if the server determines that the user is tired, a suggestion to reduce the intensity of the exercise will be added as feedback.

[0388] Step 6:

[0389] After completing a training session, the user presses the "End Session" button to send the entire session data to the server. This data (movement data, execution status of the exercise plan, and feedback history) is stored on the server and used to adjust future training plans. It is also accumulated in a database as long-term fitness history and used when creating the next plan.

[0390] (Application Example 2)

[0391] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0392] The goal is to provide a system that offers personalized fitness instruction that considers not only the user's movement patterns but also their psychological state when providing feedback. Such a system is expected to make the user's training experience more effective and motivating.

[0393] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0394] In this invention, the server includes a computing device that receives user information and generates an individualized training plan; an analysis device that receives a real-time video data stream from a terminal and performs video analysis; a feedback generation device that generates feedback regarding the user's movement patterns based on the analysis results and transmits it to the terminal; and an emotion analysis device that detects the user's emotional state and adaptively adjusts the training content accordingly. This enables fitness instruction that is tailored to the user's physical and emotional needs.

[0395] "User information" refers to data that can identify a user, including information such as fitness goals and individual physical characteristics.

[0396] A "training plan" is an exercise program tailored to the user's goals and fitness level.

[0397] A "computational device" is an electronic device used to process user information and generate an optimal training plan.

[0398] A "terminal" is a device used by a user that has the means to communicate with the system.

[0399] A "video data stream" is a continuous stream of image data that records the user's movements and actions in real time.

[0400] An "analysis device" is a device that analyzes received video data and evaluates the user's behavior.

[0401] A "feedback generation device" is a device that provides accurate advice and guidance to the user based on the results obtained from an analysis device.

[0402] An "information management device" is a device that stores and manages a user's training history and other related information.

[0403] An "emotion analysis device" is a device that determines a user's emotions from their facial expressions and behavior and reflects that in their fitness program.

[0404] This system is comprised of various technological elements combined to provide personalized fitness instruction. Users first create an account using a terminal and input their fitness goals and personal information. The terminal sends this information to a server, which uses a computing device to generate a personalized training plan for the user.

[0405] During training, the device captures the user's movements and sends them to the server as a video data stream. The server's analysis system uses image analysis libraries such as OpenCV to analyze the user's skeletal structure and movements in the video in real time. At the same time, an emotion analysis system is also running, using software such as EmotionEngine to extract emotions from the user's facial expressions.

[0406] Based on the analysis results, the server's feedback generator produces and sends to the user advice on movement patterns and psychological support messages to the terminal. The feedback is adaptively adjusted to the user's movement patterns and emotional state. This allows the user to continue receiving appropriate guidance throughout the training.

[0407] For example, if a user shows signs of discouragement during training, the server will send a message such as, "Your efforts are paying off, keep going a little longer!"

[0408] An example of a prompt message could be an instruction given to a generating AI model: "Analyze user behavior in real time and provide appropriate guidance."

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The user creates an account using their device and enters their fitness goals and personal information. The entered information is sent from the device to the server. The server receives this information and stores it in its database. Here, the input is user information, and the output is the information stored on the server.

[0412] Step 2:

[0413] The server uses computing power to process received user information and generate a personalized training plan. An AI algorithm designs the plan based on the user's goals and fitness level. The input at this stage is stored user information, and the output is a personalized training plan.

[0414] Step 3:

[0415] During training, the user uses a device to record their movements. The device sends a video data stream to the server in real time. The input is the video data of the user during training, and the output is the real-time video stream sent to the server.

[0416] Step 4:

[0417] The server's analysis device receives video data using image analysis libraries such as OpenCV and analyzes the user's skeleton and movements. It extracts coordinates from the image data and evaluates the accuracy of the movements. The input is a real-time video stream, and the output is analyzed movement data.

[0418] Step 5:

[0419] The analysis device uses EmotionEngine to extract emotions from the user's face. This converts the user's psychological state into data. The input is the user's facial expression data, and the output is numerical data of their emotional state.

[0420] Step 6:

[0421] The server's feedback generator produces feedback based on behavioral and emotional data. This is where suggested form revisions based on the analysis results and messages aimed at improving motivation are created. The input is behavioral and emotional data, and the output is a feedback message for the user.

[0422] Step 7:

[0423] The generated feedback is sent to the device and displayed to the user. The user can then adjust the training content based on this feedback. The input is the generated feedback message, and the output is what is displayed on the user's device.

[0424] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0425] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0426] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0430] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0431] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0432] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0433] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0434] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0435] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0436] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0437] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0438] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0439] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0440] The system of the present invention provides an individualized personal training environment by implementing the following main functions.

[0441] First, users create an account and complete initial setup using a mobile app or web application. Here, users enter personal information such as their name, age, gender, exercise experience, and fitness goals. The device collects this information and sends it to the server.

[0442] Based on the received user information, the server uses AI to automatically generate a training plan tailored to that user. This plan is customized to the user's training goals and includes details such as the type of exercise, number of repetitions, frequency, and intensity.

[0443] When starting a training session, the user launches the app and selects "Start Training," using their device's camera to send a real-time video stream to the server. The server receives this video stream and uses AI and image analysis technology to evaluate the user's form and movements. The analyzed data is instantly generated as feedback, providing instructions to help the user improve their form. This feedback is sent to the device via voice and text messages, and the user adjusts their training based on it.

[0444] At the end of a training session, the user selects "End Training" in the app. This sends the session data back to the server, where it is stored in the user's training history using data management tools. This history information is used to customize the next training session, allowing for adjustments to the plan based on the user's progress.

[0445] For example, if a user is performing squats, the server analyzes the user's posture in real time and provides feedback such as "You need to bend your knees more" or "Keep your torso straight," offering immediately actionable advice. In this way, users can improve the quality of their training based on the feedback, even on their own, and obtain an optimized fitness experience.

[0446] This system allows users to receive personalized training guidance anytime, anywhere.

[0447] The following describes the processing flow.

[0448] Step 1:

[0449] The user launches the app and enters information to create an account. The device retrieves this information and sends the user data along with their fitness goals to the server.

[0450] Step 2:

[0451] The server analyzes the received user information and uses an AI model to automatically generate an initial training plan based on the user's fitness level and goals. The training plan includes recommended exercises, sets, repetitions, and rest times.

[0452] Step 3:

[0453] When a user begins training, they press the "Start Training" button on their device. The device activates its camera and sends a real-time video stream of the user's movements to the server.

[0454] Step 4:

[0455] The server receives the video stream in real time and uses AI and image analysis technology to analyze the user's form and movements. It detects key points in the skeleton and posture, and evaluates whether the form is correct.

[0456] Step 5:

[0457] Based on the analysis results, the server generates feedback on the user's form. This feedback is generated in both audio and text formats and includes specific suggestions for improvement and points to note.

[0458] Step 6:

[0459] Depending on the device, feedback is displayed to the user in real time, and voice guidance prompts adjustments to their movements. The user uses this as a reference to correct their posture and movements.

[0460] Step 7:

[0461] When a user finishes training, they press the "End Training" button. The device then sends the session data to the server.

[0462] Step 8:

[0463] The server saves the received session data to the user's training history and uses it to adjust and update future training plans. This enables continuous fitness improvement.

[0464] (Example 1)

[0465] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0466] Conventional training support systems struggle to provide personalized exercise plans that meet the individual needs of each user, and they also lack sufficient real-time feedback and confirmation of movement form. As a result, users miss opportunities to learn optimal exercise methods, leading to a challenge in achieving effective training.

[0467] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0468] In this invention, the server includes a calculation means for receiving basic user information and generating an individualized exercise plan, an analysis means for receiving a real-time video stream from a terminal and performing image analysis, and a feedback generation means for generating immediate feedback on the user's exercise form based on the analysis results and transmitting it to the terminal. This makes it possible to provide training support tailored to the user's individual exercise needs and an optimal exercise experience through immediate and accurate movement evaluation.

[0469] "User basic information" refers to personal attribute data, including name, age, gender, exercise experience, and fitness goals, which users provide when registering for the application.

[0470] A "personalized exercise plan" is a training schedule that customizes the type, number of repetitions, frequency, and intensity of exercises based on each user's basic information and exercise history.

[0471] "Computational means" refers to the collective set of logical components and algorithms used to process user information within a server and generate personalized movement plans.

[0472] A "real-time video stream" is a continuous stream of video data transmitted from a terminal and transferred to a server with virtually no time delay.

[0473] "Image analysis" is a process in which a server recognizes the user's posture and movements from video data it receives and performs structural analysis.

[0474] A "feedback generation means" is a logical configuration and system that generates information pointing out areas for improvement in exercise form to the user based on the results of image analysis and transmits it to the terminal.

[0475] "Data management methods" refer to database operation techniques for systematically storing and managing users' exercise history and feedback history, and reflecting this information in future exercise plans.

[0476] A "generative AI model" is a general term for learning algorithms and models that use artificial intelligence technology to generate optimal movement plans based on user information.

[0477] A "structure detection algorithm" refers to numerical methods or mathematical calculations used to analyze the position and movement of various parts of a user's body.

[0478] This invention is a system designed to provide users with a personalized training experience. This system primarily utilizes servers, terminals, and AI technology to build a personalized exercise plan based on the user's basic information and to evaluate exercise form in real time.

[0479] First, the user accesses a dedicated application using a mobile device or computer. Here, the user enters basic information such as name, age, gender, exercise experience, and fitness goals. This information is collected on the device and transmitted to the server via Universal Networking.

[0480] The server processes the received user information and automatically generates a personalized exercise plan using a generative AI model. This plan includes the type, number of repetitions, frequency, and intensity of exercise, and is optimized to help the user achieve their goals. The AI ​​technology utilizes existing learning models and algorithms to select a plan that has a high degree of fit with the user's personal data.

[0481] When a user begins training, the device activates its built-in camera and sends the user's movements as a video stream to the server. The server analyzes this video in real time and uses image analysis technology to evaluate the user's exercise form. A specific structure detection algorithm is used in the analysis to determine how well the user's posture and movements match standard form.

[0482] Based on the analysis results, the server generates feedback on the user's exercise form, including areas for improvement and advice, and sends it to the device. The feedback is immediate and displayed on the device as voice messages or text, allowing the user to adjust their form in real time.

[0483] As a concrete example, consider a scenario where a user is performing squats. The server monitors the user's posture and provides specific feedback on knee flexion and core stability. Instructions such as "Don't let your knees go forward a little more" are communicated to the user via voice or text.

[0484] An example of a prompt message would be, "Analyze the user's squat training video and provide correct form and areas for improvement." This allows the user to continue high-quality training while making self-improvements.

[0485] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0486] Step 1:

[0487] Users access a dedicated application using their device and enter basic information such as their name, age, gender, exercise experience, and fitness goals. The entered information is collected as a dataset by the device and sent to the server. The server receives this data, stores it in a database, and uses it as input for the next processing step.

[0488] Step 2:

[0489] The server uses an AI model based on the user's basic information to generate a personalized exercise plan. User information is fed into the AI ​​algorithm, and through computational processing, an exercise plan is generated that proposes the optimal type, number of repetitions, frequency, and intensity of exercise. The exercise plan is stored in a database and sent to the user's terminal.

[0490] Step 3:

[0491] The user selects the "Start Training" button on the device to begin training. The device activates its camera and transmits the user's training as a real-time video stream to the server. At this time, the user's movement data is sent to the server as input.

[0492] Step 4:

[0493] The server analyzes the acquired video stream and uses image analysis technology to evaluate the user's movement form. Based on the input video data, a structure detection algorithm analyzes the user's posture and movements and evaluates the accuracy of the form. As a result of the analysis, the system identifies points that need correction.

[0494] Step 5:

[0495] Based on the analysis results, the server generates immediate feedback about the user's exercise form. It converts the analysis results, as input, into prompts, creating specific instructions such as "bend your knees a little more" as feedback. This feedback is then sent to the terminal.

[0496] Step 6:

[0497] The user receives feedback displayed on their device, along with warnings and advice in audio or text format. Based on this feedback, the user attempts to improve their form and movements, and adjusts their training accordingly. By accepting the feedback, the training effect can be immediately improved.

[0498] Step 7:

[0499] After completing the training session, the user presses the "End Training" button to end the session. The device sends the exercise data and feedback history collected during the session to the server, where it is stored in a database by a data management system. This history is used to optimize the next exercise plan.

[0500] (Application Example 1)

[0501] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0502] Improving worker efficiency and safety in factory operations is a challenge. Traditional work instruction is limited to general guidance, making it difficult to provide efficient, individualized feedback tailored to each worker.

[0503] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0504] In this invention, the server includes a computing means for receiving user information and generating an individualized training plan, an analysis means for receiving a real-time video stream from a terminal and performing video analysis, and a means for analyzing the worker's movements based on the analysis results and providing feedback on efficient work methods. This enables optimal movement guidance for individual workers and improved safety.

[0505] "User information" refers to basic data related to the user that is collected in order to generate a personalized training plan.

[0506] A "training plan" refers to a set of exercise and work instructions customized to a specific user's abilities and goals.

[0507] "Calculation means" refers to a device or system that performs calculations to create a customized plan based on user information.

[0508] A "real-time video stream" refers to video data that is transmitted from a terminal to a server and flows continuously without any time delay.

[0509] "Analysis means for performing video analysis" refers to a device or process for extracting meaningful information from real-time video and evaluating user movements.

[0510] "Feedback generation means" refers to a device or program that generates suggestions for improvement and effective work methods to show the user based on the analyzed data.

[0511] "Data management means" refers to a system that stores user account information, training history, and feedback history, and uses this information to inform future plans.

[0512] "Means for analyzing worker movements and providing feedback on efficient work methods" refers to devices or methods that analyze worker movements and provide guidance to improve work safety and efficiency.

[0513] The system of this invention mainly consists of three elements: a server, a terminal, and a user. The server receives user information and generates a personalized training plan using AI technology. This AI technology is implemented using widely used deep learning libraries such as TensorFlow. The generated training plan provides detailed guidance, including the type, frequency, and intensity of exercise or work.

[0514] The terminal refers to devices such as smartphones and tablets, which are the primary devices operated by the user. This terminal transmits camera footage to a server in real time, capturing the user's movements. The video data is processed by analysis tools to evaluate whether the user's movement form is correct. Image processing libraries such as OpenCV are commonly used for this analysis.

[0515] The user receives feedback through their device. The feedback generation system presents the feedback, created based on the analysis results, to the user as text or voice messages. This feedback allows the user to immediately review their actions and make improvements.

[0516] For example, when a worker operates a robotic arm in a factory, the system provides specific advice such as, "You need to tilt the robotic arm more to the right." This advice improves work efficiency and enhances safety.

[0517] An example of a prompt to be input into the generating AI model is, "Please consider what kind of action improvement advice is needed for the worker to perform their duties safely." This prompt can improve the accuracy of the feedback generated by the AI.

[0518] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0519] Step 1:

[0520] The terminal is powered on, and the user logs into the application. The user enters personal information such as name, age, and exercise experience, and sends it to the server. The entered information is stored on the server as user information.

[0521] Step 2:

[0522] The server uses AI technology to generate a personalized training plan based on the received user information. Using libraries such as TensorFlow, the optimal type, frequency, and intensity of exercise for this user are calculated. The generated training plan is stored in a database and sent to the device.

[0523] Step 3:

[0524] When a user begins training, the device's camera is activated, and a real-time video stream is sent to the server. This video captures the worker's movements and is used as data for analysis. Skeletal detection is performed using OpenCV, and the movement form is evaluated.

[0525] Step 4:

[0526] The server generates feedback on the user's actions based on the analysis results. If the user's form is inappropriate, it identifies areas for improvement and creates instructions to convey to the user through the feedback generation mechanism. For example, if the action is insufficient, text feedback such as "You need to bend your knees more" is generated.

[0527] Step 5:

[0528] Feedback is displayed on the user's device as text or voice messages. The user uses this feedback to adjust their actions and strive to perform appropriate actions. This improves operational efficiency and safety.

[0529] Step 6:

[0530] After a training session ends, session data is sent from the user's device to the server. The server receives this data and saves it as the user's training history using data management tools. This saved history is then used to generate the next training plan.

[0531] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0532] The system of this invention is designed to provide users with personalized fitness and training guidance and feedback that takes into account the user's emotions. The system is configured as follows:

[0533] First, users create an account via a mobile or web application and enter their personal information and fitness goals. The device sends this information to a server. The server uses AI technology to generate and propose a personalized training plan tailored to the user's needs.

[0534] During training, the device captures the user's video in real time and sends the video stream to the server. Upon receiving the video data, the server uses image analysis technology to analyze the skeletal structure and movements. The analyzed data is used to evaluate the user's movement form and generate specific feedback.

[0535] Furthermore, the system incorporates an emotion engine, allowing the server to analyze the user's emotions from their facial expressions and behavior. This analysis measures the user's motivation and stress levels, enabling the system to adjust feedback and training content accordingly. For example, if a user is tired, the system might recommend relaxing stretches rather than strenuous exercise.

[0536] Furthermore, based on the user's emotional state, the server generates and sends positive, personalized coaching messages to the user's device. These messages take into account the user's psychological state and support their motivation for training. For example, if the server detects that the user is feeling discouraged, it will provide encouraging messages such as, "Your efforts are paying off; by continuing, you will get closer to your goal."

[0537] At the end of a training session, the user saves all data using the session end button and sends it to the server. This data is stored for long-term performance improvement and used to adjust future plans.

[0538] This system allows users to receive training tailored to their physical and emotional needs, resulting in more consistent motivation and more effective fitness improvements.

[0539] The following describes the processing flow.

[0540] Step 1:

[0541] The user launches the app and enters the necessary personal information and fitness goals to create an account. The device then sends this information to the server.

[0542] Step 2:

[0543] The server analyzes the received user information and uses AI technology to generate a personalized training plan. The training plan includes specific exercises based on the user's exercise experience and goals.

[0544] Step 3:

[0545] When a user begins training, the device's camera is activated, and the user's video is sent to the server in real time. The device captures and transmits the video data.

[0546] Step 4:

[0547] The server uses skeletal detection and motion analysis algorithms to evaluate the user's movement form in order to analyze the received real-time video.

[0548] Step 5:

[0549] Based on the analysis results, the server generates feedback for improving forms and performance, and sends this feedback to the device. This feedback is notified to the user via voice or text.

[0550] Step 6:

[0551] The server further analyzes the user's facial expressions from the video data and uses an emotion engine to evaluate the user's emotional state. This emotion data is used to adjust the difficulty level of the training.

[0552] Step 7:

[0553] The device provides users with feedback and motivational messages that reflect their emotional state. This allows users to receive appropriate guidance based on their emotions.

[0554] Step 8:

[0555] After the training session ends, the user presses the "End Training" button on their device to send the session data to the server. The server saves the data and uses it to help plan the next training session.

[0556] (Example 2)

[0557] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0558] There are challenges in fitness and training, such as the difficulty users receive guidance that takes into account their individual physical condition and emotional state, making it difficult to achieve results with general plans. Furthermore, the lack of real-time feedback and long-term data utilization makes it difficult for users to maintain their motivation.

[0559] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0560] In this invention, the server includes a computation means for receiving user information and generating an individualized exercise plan using a generated artificial intelligence model; an analysis means for receiving a real-time image data stream and performing video analysis; and an emotion analysis means for analyzing the user's emotions and reflecting them in the movement plan and feedback. This makes it possible to provide personalized training that takes into account not only the user's physical condition but also their emotional state.

[0561] "User information" refers to personal data provided by the user, including name, age, gender, and fitness goals.

[0562] A "generative artificial intelligence model" is a technology that uses machine learning algorithms to analyze movement patterns and emotions, and then generates personalized motor plans.

[0563] An "exercise plan" is a specific schedule or guideline of fitness and training activities tailored to the individual user's physical and emotional condition.

[0564] "Computation means" refers to a computer system or its components for processing user information and generating personalized movement plans.

[0565] A "real-time image data stream" is a continuous stream of video data sent from a terminal to a server to record user activity.

[0566] "Video analysis" is a process that uses image analysis technology to analyze and evaluate user behavior from received video data.

[0567] "Analysis means" refers to a device or program equipped with image analysis technology for the purpose of processing video data and analyzing the user's behavior patterns.

[0568] "Motion style" refers to the structure and arrangement of the user's physical movements and poses.

[0569] A "feedback generation means" is a system that has the function of generating guidance and improvement suggestions regarding the user's actions based on the analyzed data and sending them to the terminal.

[0570] "Emotional analysis" is a process that evaluates a user's emotional state based on their facial expressions and behavior, and measures their motivation, stress levels, and other factors.

[0571] An "emotion analysis tool" is a system or program that processes facial expression and behavioral data in order to analyze a user's emotions.

[0572] "Information management means" refers to a system that organizes, stores, and manages users' training history, feedback history, and account information.

[0573] The system of this invention provides personalized fitness and training guidance that also takes emotional aspects into consideration. This system is configured as follows:

[0574] First, users enter their personal information and fitness goals using a mobile or web-based device. This information is transmitted to a server via the internet. The server uses a generative AI model to generate a personalized exercise plan based on the user's information. This model is built using machine learning algorithms and develops new plans based on the latest training data and past user history.

[0575] When a user begins training, the device uses its built-in camera to capture the user's movements in real time and streams the video data to the server. The server then uses image analysis technology to analyze the received video data and the user's movements. This analysis, which utilizes open pose and deep learning, evaluates the user's skeletal structure and movement patterns, and generates feedback.

[0576] Furthermore, the system incorporates an emotion analysis engine. The server receives the user's facial expression data and analyzes their emotional state. Based on this analysis, it evaluates the user's motivation and stress level and adjusts the training content by providing appropriate feedback. For example, it might suggest relaxing stretches to a tired user, or send a message to a user feeling discouraged, such as "Your efforts are paying off; continuing will bring you closer to your goal."

[0577] After a training session ends, the user presses the "End Session" button to send all session data to the server. This transmitted data is stored as a long-term fitness history and used to adjust future exercise plans.

[0578] As a concrete example, here is an example of a prompt statement for a generative AI model that issues instructions to the system:

[0579] "Based on the user's fitness data and emotional state, suggest a training plan for their next session."

[0580] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0581] Step 1:

[0582] Users open the fitness app on their device, create an account, and enter their personal information and fitness goals. This information is sent to the server via the device. The entered data is stored in a database on the server and serves as the basis for generating personalized exercise plans.

[0583] Step 2:

[0584] The server receives the user's personal information and goal data, and then uses a generative AI model to create a personalized exercise plan. Input data includes age, gender, fitness level, and goals (e.g., weight loss, muscle gain). The server processes this data and uses a machine learning algorithm to calculate the optimal exercise plan. The generated exercise plan is sent to the user's device and displayed within the app.

[0585] Step 3:

[0586] When a user begins exercising, the device uses its built-in camera to capture real-time video of the user. This video data is streamed to a server. The server analyzes the received video and uses image analysis technology to analyze the user's movements. The input data is a video stream, and the accuracy and efficiency of the movements are evaluated based on this. Useful feedback is returned to the device.

[0587] Step 4:

[0588] The server generates specific feedback for the user based on the analyzed motion data. From the results obtained from the analysis (e.g., posture, motion accuracy), it identifies areas for improvement in the user's movements and creates advice based on those areas. The generated feedback is sent to the terminal, allowing the user to view it in real time.

[0589] Step 5:

[0590] During training, the server performs emotion analysis by receiving data from the user's facial expressions. The input includes videos of the user, which the server analyzes to measure the user's motivation and stress level. Based on the emotion analysis results, the training content and feedback are adjusted in real time. For example, if the server determines that the user is tired, a suggestion to reduce the intensity of the exercise will be added as feedback.

[0591] Step 6:

[0592] After completing a training session, the user presses the "End Session" button to send the entire session data to the server. This data (movement data, execution status of the exercise plan, and feedback history) is stored on the server and used to adjust future training plans. It is also accumulated in a database as long-term fitness history and used when creating the next plan.

[0593] (Application Example 2)

[0594] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0595] The goal is to provide a system that offers personalized fitness instruction that considers not only the user's movement patterns but also their psychological state when providing feedback. Such a system is expected to make the user's training experience more effective and motivating.

[0596] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0597] In this invention, the server includes a computing device that receives user information and generates an individualized training plan; an analysis device that receives a real-time video data stream from a terminal and performs video analysis; a feedback generation device that generates feedback regarding the user's movement patterns based on the analysis results and transmits it to the terminal; and an emotion analysis device that detects the user's emotional state and adaptively adjusts the training content accordingly. This enables fitness instruction that is tailored to the user's physical and emotional needs.

[0598] "User information" refers to data that can identify a user, including information such as fitness goals and individual physical characteristics.

[0599] A "training plan" is an exercise program tailored to the user's goals and fitness level.

[0600] A "computational device" is an electronic device used to process user information and generate an optimal training plan.

[0601] A "terminal" is a device used by a user that has the means to communicate with the system.

[0602] A "video data stream" is a continuous stream of image data that records the user's movements and actions in real time.

[0603] An "analysis device" is a device that analyzes received video data and evaluates the user's behavior.

[0604] A "feedback generation device" is a device that provides accurate advice and guidance to the user based on the results obtained from an analysis device.

[0605] An "information management device" is a device that stores and manages a user's training history and other related information.

[0606] An "emotion analysis device" is a device that determines a user's emotions from their facial expressions and behavior and reflects that in their fitness program.

[0607] This system combines various technological elements to provide personalized fitness instruction. Users first create an account using a terminal and input their fitness goals and personal information. The terminal sends this information to a server, which uses a computing device to generate a personalized training plan for the user.

[0608] During training, the device captures the user's movements and sends them to the server as a video data stream. The server's analysis system uses image analysis libraries such as OpenCV to analyze the user's skeletal structure and movements in the video in real time. At the same time, an emotion analysis system is also running, using software such as EmotionEngine to extract emotions from the user's facial expressions.

[0609] Based on the analysis results, the server's feedback generator produces and sends to the user advice on movement patterns and psychological support messages to the terminal. The feedback is adaptively adjusted to the user's movement patterns and emotional state. This allows the user to continue receiving appropriate guidance throughout the training.

[0610] For example, if a user shows signs of discouragement during training, the server will send a message such as, "Your efforts are paying off, keep going a little longer!"

[0611] An example of a prompt message could be an instruction given to a generating AI model: "Analyze user behavior in real time and provide appropriate guidance."

[0612] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0613] Step 1:

[0614] The user creates an account using their device and enters their fitness goals and personal information. The entered information is sent from the device to the server. The server receives this information and stores it in its database. Here, the input is user information, and the output is the information stored on the server.

[0615] Step 2:

[0616] The server uses computing power to process received user information and generate a personalized training plan. An AI algorithm designs the plan based on the user's goals and fitness level. The input at this stage is stored user information, and the output is a personalized training plan.

[0617] Step 3:

[0618] During training, the user uses a device to record their movements. The device sends a video data stream to the server in real time. The input is the video data of the user during training, and the output is the real-time video stream sent to the server.

[0619] Step 4:

[0620] The server's analysis device receives video data using image analysis libraries such as OpenCV and analyzes the user's skeleton and movements. It extracts coordinates from the image data and evaluates the accuracy of the movements. The input is a real-time video stream, and the output is analyzed movement data.

[0621] Step 5:

[0622] The analysis device uses EmotionEngine to extract emotions from the user's face. This converts the user's psychological state into data. The input is the user's facial expression data, and the output is numerical data of their emotional state.

[0623] Step 6:

[0624] The server's feedback generator produces feedback based on behavioral and emotional data. This is where suggested form revisions based on the analysis results and messages aimed at improving motivation are created. The input is behavioral and emotional data, and the output is a feedback message for the user.

[0625] Step 7:

[0626] The generated feedback is sent to the device and displayed to the user. The user can then adjust the training content based on this feedback. The input is the generated feedback message, and the output is what is displayed on the user's device.

[0627] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0628] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0629] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0630] [Fourth Embodiment]

[0631] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0632] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0633] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0634] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0635] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0636] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0637] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0638] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0639] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0640] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0641] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0642] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0643] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0644] The system of the present invention provides an individualized personal training environment by implementing the following main functions.

[0645] First, users create an account and complete initial setup using a mobile app or web application. Here, users enter personal information such as their name, age, gender, exercise experience, and fitness goals. The device collects this information and sends it to the server.

[0646] Based on the received user information, the server uses AI to automatically generate a training plan tailored to that user. This plan is customized to the user's training goals and includes details such as the type of exercise, number of repetitions, frequency, and intensity.

[0647] When starting a training session, the user launches the app and selects "Start Training," using their device's camera to send a real-time video stream to the server. The server receives this video stream and uses AI and image analysis technology to evaluate the user's form and movements. The analyzed data is instantly generated as feedback, providing instructions to help the user improve their form. This feedback is sent to the device via voice and text messages, and the user adjusts their training based on it.

[0648] At the end of a training session, the user selects "End Training" in the app. This sends the session data back to the server, where it is stored in the user's training history using data management tools. This history information is used to customize the next training session, allowing for adjustments to the plan based on the user's progress.

[0649] For example, if a user is performing squats, the server analyzes the user's posture in real time and provides feedback such as "You need to bend your knees more" or "Keep your torso straight," offering immediately actionable advice. In this way, users can improve the quality of their training based on the feedback, even on their own, and obtain an optimized fitness experience.

[0650] This system allows users to receive personalized training guidance anytime, anywhere.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] The user launches the app and enters information to create an account. The device retrieves this information and sends the user data along with their fitness goals to the server.

[0654] Step 2:

[0655] The server analyzes the received user information and uses an AI model to automatically generate an initial training plan based on the user's fitness level and goals. The training plan includes recommended exercises, sets, repetitions, and rest times.

[0656] Step 3:

[0657] When a user begins training, they press the "Start Training" button on their device. The device activates its camera and sends a real-time video stream of the user's movements to the server.

[0658] Step 4:

[0659] The server receives the video stream in real time and uses AI and image analysis technology to analyze the user's form and movements. It detects key points in the skeleton and posture, and evaluates whether the form is correct.

[0660] Step 5:

[0661] Based on the analysis results, the server generates feedback on the user's form. This feedback is generated in both audio and text formats and includes specific suggestions for improvement and points to note.

[0662] Step 6:

[0663] Depending on the device, feedback is displayed to the user in real time, and voice guidance prompts adjustments to their movements. The user uses this as a reference to correct their posture and movements.

[0664] Step 7:

[0665] When a user finishes training, they press the "End Training" button. The device then sends the session data to the server.

[0666] Step 8:

[0667] The server saves the received session data to the user's training history and uses it to adjust and update future training plans. This enables continuous fitness improvement.

[0668] (Example 1)

[0669] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0670] Conventional training support systems struggle to provide personalized exercise plans that meet the individual needs of each user, and they also lack sufficient real-time feedback and confirmation of movement form. As a result, users miss opportunities to learn optimal exercise methods, leading to a challenge in achieving effective training.

[0671] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0672] In this invention, the server includes a calculation means for receiving basic user information and generating an individualized exercise plan, an analysis means for receiving a real-time video stream from a terminal and performing image analysis, and a feedback generation means for generating immediate feedback on the user's exercise form based on the analysis results and transmitting it to the terminal. This makes it possible to provide training support tailored to the user's individual exercise needs and an optimal exercise experience through immediate and accurate movement evaluation.

[0673] "User basic information" refers to personal attribute data, including name, age, gender, exercise experience, and fitness goals, which users provide when registering for the application.

[0674] A "personalized exercise plan" is a training schedule that customizes the type, number of repetitions, frequency, and intensity of exercises based on each user's basic information and exercise history.

[0675] "Computational means" refers to the collective set of logical components and algorithms used to process user information within a server and generate personalized movement plans.

[0676] A "real-time video stream" is a continuous stream of video data transmitted from a terminal and transferred to a server with virtually no time delay.

[0677] "Image analysis" is a process in which a server recognizes the user's posture and movements from video data it receives and performs structural analysis.

[0678] A "feedback generation means" is a logical configuration and system that generates information pointing out areas for improvement in exercise form to the user based on the results of image analysis and transmits it to the terminal.

[0679] "Data management methods" refer to database operation techniques for systematically storing and managing users' exercise history and feedback history, and reflecting this information in future exercise plans.

[0680] A "generative AI model" is a general term for learning algorithms and models that use artificial intelligence technology to generate optimal movement plans based on user information.

[0681] A "structure detection algorithm" refers to numerical methods or mathematical calculations used to analyze the position and movement of various parts of a user's body.

[0682] This invention is a system designed to provide users with a personalized training experience. This system primarily utilizes servers, terminals, and AI technology to build a personalized exercise plan based on the user's basic information and to evaluate exercise form in real time.

[0683] First, the user accesses a dedicated application using a mobile device or computer. Here, the user enters basic information such as name, age, gender, exercise experience, and fitness goals. This information is collected on the device and transmitted to the server via Universal Networking.

[0684] The server processes the received user information and automatically generates a personalized exercise plan using a generative AI model. This plan includes the type, number of repetitions, frequency, and intensity of exercise, and is optimized to help the user achieve their goals. The AI ​​technology utilizes existing learning models and algorithms to select a plan that has a high degree of fit with the user's personal data.

[0685] When a user begins training, the device activates its built-in camera and sends the user's movements as a video stream to the server. The server analyzes this video in real time and uses image analysis technology to evaluate the user's exercise form. A specific structure detection algorithm is used in the analysis to determine how well the user's posture and movements match standard form.

[0686] Based on the analysis results, the server generates feedback on the user's exercise form, including areas for improvement and advice, and sends it to the device. The feedback is immediate and displayed on the device as voice messages or text, allowing the user to adjust their form in real time.

[0687] As a concrete example, consider a scenario where a user is performing squats. The server monitors the user's posture and provides specific feedback on knee flexion and core stability. Instructions such as "Don't let your knees go forward a little more" are communicated to the user via voice or text.

[0688] An example of a prompt message would be, "Analyze the user's squat training video and provide correct form and areas for improvement." This allows the user to continue high-quality training while making self-improvements.

[0689] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0690] Step 1:

[0691] Users access a dedicated application using their device and enter basic information such as their name, age, gender, exercise experience, and fitness goals. The entered information is collected as a dataset by the device and sent to the server. The server receives this data, stores it in a database, and uses it as input for the next processing step.

[0692] Step 2:

[0693] The server uses an AI model based on the user's basic information to generate a personalized exercise plan. User information is fed into the AI ​​algorithm, and through computational processing, an exercise plan is generated that proposes the optimal type, number of repetitions, frequency, and intensity of exercise. The exercise plan is stored in a database and sent to the user's terminal.

[0694] Step 3:

[0695] The user selects the "Start Training" button on the device to begin training. The device activates its camera and transmits the user's training as a real-time video stream to the server. At this time, the user's movement data is sent to the server as input.

[0696] Step 4:

[0697] The server analyzes the acquired video stream and uses image analysis technology to evaluate the user's movement form. Based on the input video data, a structure detection algorithm analyzes the user's posture and movements and evaluates the accuracy of the form. As a result of the analysis, the system identifies points that need correction.

[0698] Step 5:

[0699] Based on the analysis results, the server generates immediate feedback about the user's exercise form. It converts the analysis results, as input, into prompts, creating specific instructions such as "bend your knees a little more" as feedback. This feedback is then sent to the terminal.

[0700] Step 6:

[0701] The user receives feedback displayed on their device, along with warnings and advice in audio or text format. Based on this feedback, the user attempts to improve their form and movements, and adjusts their training accordingly. By accepting the feedback, the training effect can be immediately improved.

[0702] Step 7:

[0703] After completing the training session, the user presses the "End Training" button to end the session. The device sends the exercise data and feedback history collected during the session to the server, where it is stored in a database by a data management system. This history is used to optimize the next exercise plan.

[0704] (Application Example 1)

[0705] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0706] Improving worker efficiency and safety in factory operations is a challenge. Traditional work instruction is limited to general guidance, making it difficult to provide efficient, individualized feedback tailored to each worker.

[0707] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0708] In this invention, the server includes a computing means for receiving user information and generating an individualized training plan, an analysis means for receiving a real-time video stream from a terminal and performing video analysis, and a means for analyzing the worker's movements based on the analysis results and providing feedback on efficient work methods. This enables optimal movement guidance for individual workers and improved safety.

[0709] "User information" refers to basic data related to the user that is collected in order to generate a personalized training plan.

[0710] A "training plan" refers to a set of exercise and work instructions customized to a specific user's abilities and goals.

[0711] "Calculation means" refers to a device or system that performs calculations to create a customized plan based on user information.

[0712] A "real-time video stream" refers to video data that is transmitted from a terminal to a server and flows continuously without any time delay.

[0713] "Analysis means for performing video analysis" refers to a device or process for extracting meaningful information from real-time video and evaluating user movements.

[0714] "Feedback generation means" refers to a device or program that generates suggestions for improvement and effective work methods to show the user based on the analyzed data.

[0715] "Data management means" refers to a system that stores user account information, training history, and feedback history, and uses this information to inform future plans.

[0716] "Means for analyzing worker movements and providing feedback on efficient work methods" refers to devices or methods that analyze worker movements and provide guidance to improve work safety and efficiency.

[0717] The system of this invention mainly consists of three elements: a server, a terminal, and a user. The server receives user information and generates a personalized training plan using AI technology. This AI technology is implemented using widely used deep learning libraries such as TensorFlow. The generated training plan provides detailed guidance, including the type, frequency, and intensity of exercise or work.

[0718] The terminal refers to devices such as smartphones and tablets, which are the primary devices operated by the user. This terminal transmits camera footage to a server in real time, capturing the user's movements. The video data is processed by analysis tools to evaluate whether the user's movement form is correct. Image processing libraries such as OpenCV are commonly used for this analysis.

[0719] The user receives feedback through their device. The feedback generation system presents the feedback, created based on the analysis results, to the user as text or voice messages. This feedback allows the user to immediately review their actions and make improvements.

[0720] For example, when a worker operates a robotic arm in a factory, the system provides specific advice such as, "You need to tilt the robotic arm more to the right." This advice improves work efficiency and enhances safety.

[0721] An example of a prompt to be input into the generating AI model is, "Please consider what kind of action improvement advice is needed for the worker to perform their duties safely." This prompt can improve the accuracy of the feedback generated by the AI.

[0722] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0723] Step 1:

[0724] The terminal is powered on, and the user logs into the application. The user enters personal information such as name, age, and exercise experience, and sends it to the server. The entered information is stored on the server as user information.

[0725] Step 2:

[0726] The server uses AI technology to generate a personalized training plan based on the received user information. Using libraries such as TensorFlow, the optimal type, frequency, and intensity of exercise for this user are calculated. The generated training plan is stored in a database and sent to the device.

[0727] Step 3:

[0728] When a user begins training, the device's camera is activated, and a real-time video stream is sent to the server. This video captures the worker's movements and is used as data for analysis. Skeletal detection is performed using OpenCV, and the movement form is evaluated.

[0729] Step 4:

[0730] The server generates feedback on the user's actions based on the analysis results. If the user's form is inappropriate, it identifies areas for improvement and creates instructions to convey to the user through the feedback generation mechanism. For example, if the action is insufficient, text feedback such as "You need to bend your knees more" is generated.

[0731] Step 5:

[0732] Feedback is displayed on the user's device as text or voice messages. The user uses this feedback to adjust their actions and strive to perform appropriate actions. This improves operational efficiency and safety.

[0733] Step 6:

[0734] After a training session ends, session data is sent from the user's device to the server. The server receives this data and saves it as the user's training history using data management tools. This saved history is then used to generate the next training plan.

[0735] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0736] The system of this invention is designed to provide users with personalized fitness and training guidance and feedback that takes into account the user's emotions. The system is configured as follows:

[0737] First, users create an account via a mobile or web application and enter their personal information and fitness goals. The device sends this information to a server. The server uses AI technology to generate and propose a personalized training plan tailored to the user's needs.

[0738] During training, the device captures the user's video in real time and sends the video stream to the server. Upon receiving the video data, the server uses image analysis technology to analyze the skeletal structure and movements. The analyzed data is used to evaluate the user's movement form and generate specific feedback.

[0739] Furthermore, the system incorporates an emotion engine, allowing the server to analyze the user's emotions from their facial expressions and behavior. This analysis measures the user's motivation and stress levels, enabling the system to adjust feedback and training content accordingly. For example, if a user is tired, the system might recommend relaxing stretches rather than strenuous exercise.

[0740] Furthermore, based on the user's emotional state, the server generates and sends positive, personalized coaching messages to the user's device. These messages take into account the user's psychological state and support their motivation for training. For example, if the server detects that the user is feeling discouraged, it will provide encouraging messages such as, "Your efforts are paying off; by continuing, you will get closer to your goal."

[0741] At the end of a training session, the user saves all data using the session end button and sends it to the server. This data is stored for long-term performance improvement and used to adjust future plans.

[0742] This system allows users to receive training tailored to their physical and emotional needs, resulting in more consistent motivation and more effective fitness improvements.

[0743] The following describes the processing flow.

[0744] Step 1:

[0745] The user launches the app and enters the necessary personal information and fitness goals to create an account. The device then sends this information to the server.

[0746] Step 2:

[0747] The server analyzes the received user information and uses AI technology to generate a personalized training plan. The training plan includes specific exercises based on the user's exercise experience and goals.

[0748] Step 3:

[0749] When a user begins training, the device's camera is activated, and the user's video is sent to the server in real time. The device captures and transmits the video data.

[0750] Step 4:

[0751] The server uses skeletal detection and motion analysis algorithms to evaluate the user's movement form in order to analyze the received real-time video.

[0752] Step 5:

[0753] Based on the analysis results, the server generates feedback for improving forms and performance, and sends this feedback to the device. This feedback is notified to the user via voice or text.

[0754] Step 6:

[0755] The server further analyzes the user's facial expressions from the video data and uses an emotion engine to evaluate the user's emotional state. This emotion data is used to adjust the difficulty level of the training.

[0756] Step 7:

[0757] The device provides users with feedback and motivational messages that reflect their emotional state. This allows users to receive appropriate guidance based on their emotions.

[0758] Step 8:

[0759] After the training session ends, the user presses the "End Training" button on their device to send the session data to the server. The server saves the data and uses it to help plan the next training session.

[0760] (Example 2)

[0761] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0762] There are challenges in fitness and training, such as the difficulty users receive guidance that takes into account their individual physical condition and emotional state, making it difficult to achieve results with general plans. Furthermore, the lack of real-time feedback and long-term data utilization makes it difficult for users to maintain their motivation.

[0763] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0764] In this invention, the server includes a computation means for receiving user information and generating an individualized exercise plan using a generated artificial intelligence model; an analysis means for receiving a real-time image data stream and performing video analysis; and an emotion analysis means for analyzing the user's emotions and reflecting them in the movement plan and feedback. This makes it possible to provide personalized training that takes into account not only the user's physical condition but also their emotional state.

[0765] "User information" refers to personal data provided by the user, including name, age, gender, and fitness goals.

[0766] A "generative artificial intelligence model" is a technology that uses machine learning algorithms to analyze movement patterns and emotions, and then generates personalized motor plans.

[0767] An "exercise plan" is a specific schedule or guideline of fitness and training activities tailored to the individual user's physical and emotional condition.

[0768] "Computation means" refers to a computer system or its components for processing user information and generating personalized movement plans.

[0769] A "real-time image data stream" is a continuous stream of video data sent from a terminal to a server to record user activity.

[0770] "Video analysis" is a process that uses image analysis technology to analyze and evaluate user behavior from received video data.

[0771] "Analysis means" refers to a device or program equipped with image analysis technology for the purpose of processing video data and analyzing the user's behavior patterns.

[0772] "Motion style" refers to the structure and arrangement of the user's physical movements and poses.

[0773] A "feedback generation means" is a system that has the function of generating guidance and improvement suggestions regarding the user's actions based on the analyzed data and sending them to the terminal.

[0774] "Emotional analysis" is a process that evaluates a user's emotional state based on their facial expressions and behavior, and measures their motivation, stress levels, and other factors.

[0775] An "emotion analysis tool" is a system or program that processes facial expression and behavioral data in order to analyze a user's emotions.

[0776] "Information management means" refers to a system that organizes, stores, and manages users' training history, feedback history, and account information.

[0777] The system of this invention provides personalized fitness and training guidance that also takes emotional aspects into consideration. This system is configured as follows:

[0778] First, users enter their personal information and fitness goals using a mobile or web-based device. This information is transmitted to a server via the internet. The server uses a generative AI model to generate a personalized exercise plan based on the user's information. This model is built using machine learning algorithms and develops new plans based on the latest training data and past user history.

[0779] When a user begins training, the device uses its built-in camera to capture the user's movements in real time and streams the video data to the server. The server then uses image analysis technology to analyze the received video data and the user's movements. This analysis, which utilizes open pose and deep learning, evaluates the user's skeletal structure and movement patterns, and generates feedback.

[0780] Furthermore, the system incorporates an emotion analysis engine. The server receives the user's facial expression data and analyzes their emotional state. Based on this analysis, it evaluates the user's motivation and stress level and adjusts the training content by providing appropriate feedback. For example, it might suggest relaxing stretches to a tired user, or send a message to a user feeling discouraged, such as "Your efforts are paying off; continuing will bring you closer to your goal."

[0781] After a training session ends, the user presses the "End Session" button to send all session data to the server. This transmitted data is stored as a long-term fitness history and used to adjust future exercise plans.

[0782] As a concrete example, here is an example of a prompt statement for a generative AI model that issues instructions to the system:

[0783] "Based on the user's fitness data and emotional state, suggest a training plan for their next session."

[0784] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0785] Step 1:

[0786] Users open the fitness app on their device, create an account, and enter their personal information and fitness goals. This information is sent to the server via the device. The entered data is stored in a database on the server and serves as the basis for generating personalized exercise plans.

[0787] Step 2:

[0788] The server receives the user's personal information and goal data, and then uses a generative AI model to create a personalized exercise plan. Input data includes age, gender, fitness level, and goals (e.g., weight loss, muscle gain). The server processes this data and uses a machine learning algorithm to calculate the optimal exercise plan. The generated exercise plan is sent to the user's device and displayed within the app.

[0789] Step 3:

[0790] When a user begins exercising, the device uses its built-in camera to capture real-time video of the user. This video data is streamed to a server. The server analyzes the received video and uses image analysis technology to analyze the user's movements. The input data is a video stream, and the accuracy and efficiency of the movements are evaluated based on this. Useful feedback is returned to the device.

[0791] Step 4:

[0792] The server generates specific feedback for the user based on the analyzed motion data. From the results obtained from the analysis (e.g., posture, motion accuracy), it identifies areas for improvement in the user's movements and creates advice based on those areas. The generated feedback is sent to the terminal, allowing the user to view it in real time.

[0793] Step 5:

[0794] During training, the server performs emotion analysis by receiving data from the user's facial expressions. The input includes videos of the user, which the server analyzes to measure the user's motivation and stress level. Based on the emotion analysis results, the training content and feedback are adjusted in real time. For example, if the server determines that the user is tired, a suggestion to reduce the intensity of the exercise will be added as feedback.

[0795] Step 6:

[0796] After completing a training session, the user presses the "End Session" button to send the entire session data to the server. This data (movement data, execution status of the exercise plan, and feedback history) is stored on the server and used to adjust future training plans. It is also accumulated in a database as long-term fitness history and used when creating the next plan.

[0797] (Application Example 2)

[0798] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0799] The goal is to provide a system that offers personalized fitness instruction that considers not only the user's movement patterns but also their psychological state when providing feedback. Such a system is expected to make the user's training experience more effective and motivating.

[0800] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0801] In this invention, the server includes a computing device that receives user information and generates an individualized training plan; an analysis device that receives a real-time video data stream from a terminal and performs video analysis; a feedback generation device that generates feedback regarding the user's movement patterns based on the analysis results and transmits it to the terminal; and an emotion analysis device that detects the user's emotional state and adaptively adjusts the training content accordingly. This enables fitness instruction that is tailored to the user's physical and emotional needs.

[0802] "User information" refers to data that can identify a user, including information such as fitness goals and individual physical characteristics.

[0803] A "training plan" is an exercise program tailored to the user's goals and fitness level.

[0804] A "computational device" is an electronic device used to process user information and generate an optimal training plan.

[0805] A "terminal" is a device used by a user that has the means to communicate with the system.

[0806] A "video data stream" is a continuous stream of image data that records the user's movements and actions in real time.

[0807] An "analysis device" is a device that analyzes received video data and evaluates the user's behavior.

[0808] A "feedback generation device" is a device that provides accurate advice and guidance to the user based on the results obtained from an analysis device.

[0809] An "information management device" is a device that stores and manages a user's training history and other related information.

[0810] An "emotion analysis device" is a device that determines a user's emotions from their facial expressions and behavior and reflects that in their fitness program.

[0811] This system combines various technological elements to provide personalized fitness instruction. Users first create an account using a terminal and input their fitness goals and personal information. The terminal sends this information to a server, which uses a computing device to generate a personalized training plan for the user.

[0812] During training, the device captures the user's movements and sends them to the server as a video data stream. The server's analysis system uses image analysis libraries such as OpenCV to analyze the user's skeletal structure and movements in the video in real time. At the same time, an emotion analysis system is also running, using software such as EmotionEngine to extract emotions from the user's facial expressions.

[0813] Based on the analysis results, the server's feedback generator produces and sends to the user advice on movement patterns and psychological support messages to the terminal. The feedback is adaptively adjusted to the user's movement patterns and emotional state. This allows the user to continue receiving appropriate guidance throughout the training.

[0814] For example, if a user shows signs of discouragement during training, the server will send a message such as, "Your efforts are paying off, keep going a little longer!"

[0815] An example of a prompt message could be an instruction given to a generating AI model: "Analyze user behavior in real time and provide appropriate guidance."

[0816] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0817] Step 1:

[0818] The user creates an account using their device and enters their fitness goals and personal information. The entered information is sent from the device to the server. The server receives this information and stores it in its database. Here, the input is user information, and the output is the information stored on the server.

[0819] Step 2:

[0820] The server uses computing power to process received user information and generate a personalized training plan. An AI algorithm designs the plan based on the user's goals and fitness level. The input at this stage is stored user information, and the output is a personalized training plan.

[0821] Step 3:

[0822] During training, the user uses a device to record their movements. The device sends a video data stream to the server in real time. The input is the video data of the user during training, and the output is the real-time video stream sent to the server.

[0823] Step 4:

[0824] The server's analysis device receives video data using image analysis libraries such as OpenCV and analyzes the user's skeleton and movements. It extracts coordinates from the image data and evaluates the accuracy of the movements. The input is a real-time video stream, and the output is analyzed movement data.

[0825] Step 5:

[0826] The analysis device uses EmotionEngine to extract emotions from the user's face. This converts the user's psychological state into data. The input is the user's facial expression data, and the output is numerical data of their emotional state.

[0827] Step 6:

[0828] The server's feedback generator produces feedback based on behavioral and emotional data. This is where suggested form revisions based on the analysis results and messages aimed at improving motivation are created. The input is behavioral and emotional data, and the output is a feedback message for the user.

[0829] Step 7:

[0830] The generated feedback is sent to the device and displayed to the user. The user can then adjust the training content based on this feedback. The input is the generated feedback message, and the output is what is displayed on the user's device.

[0831] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0832] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0833] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0834] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0835] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0836] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0837] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0838] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0839] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0840] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0841] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0842] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0843] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0844] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0845] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0846] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0847] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0848] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0849] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0850] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0851] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0852] The following is further disclosed regarding the embodiments described above.

[0853] (Claim 1)

[0854] A computation means that receives user information and generates an individualized training plan,

[0855] An analysis means that receives a real-time video stream from a terminal and performs video analysis,

[0856] A feedback generation means generates feedback regarding the user's action form based on the analysis results and sends it to the terminal,

[0857] A data management system that saves the user's training history and reflects it in the next training plan,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, characterized in that the data management means manages user account information, training history, and feedback history.

[0861] (Claim 3)

[0862] The system according to claim 1, characterized in that the analysis means analyzes the user's movement form using a skeletal detection algorithm.

[0863] "Example 1"

[0864] (Claim 1)

[0865] A computing means that receives basic user information and generates an individualized exercise plan,

[0866] An analysis means that receives a real-time video stream from a terminal and performs image analysis,

[0867] A feedback generation means that generates immediate feedback on the user's exercise form based on the analysis results and transmits it to the terminal,

[0868] A data management system that saves the user's exercise history and reflects it in the next exercise plan,

[0869] An optimization method that automatically constructs an optimized exercise plan for the user using a generative AI model,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, characterized in that the data management means manages the user's registration information, exercise history, and feedback history.

[0873] (Claim 3)

[0874] The system according to claim 1, characterized in that the analysis means analyzes the user's movement form using a structure detection algorithm.

[0875] "Application Example 1"

[0876] (Claim 1)

[0877] A computation means that receives user information and generates an individualized training plan,

[0878] An analysis means that receives a real-time video stream from a terminal and performs video analysis,

[0879] A feedback generation means generates feedback regarding the user's action form based on the analysis results and sends it to the terminal,

[0880] A data management system that saves the user's training history and reflects it in the next training plan,

[0881] A means of analyzing the worker's movements and providing feedback on efficient work methods,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, characterized in that the data management means manages user account information, training history, and feedback history.

[0885] (Claim 3)

[0886] The system according to claim 1, characterized in that the analysis means analyzes the user's movement form using a skeletal detection algorithm and determines actions to improve work efficiency.

[0887] "Example 2 of combining an emotion engine"

[0888] (Claim 1)

[0889] A computation means that receives user information and generates an individualized motor plan using a generated artificial intelligence model,

[0890] An analysis means that receives a real-time image data stream from a terminal and performs video analysis,

[0891] A feedback generation means generates feedback regarding the user's behavior based on the analysis results and sends it to the terminal,

[0892] A means of analyzing user emotions and reflecting them in action plans and feedback,

[0893] An information management system that saves the user's training history and reflects it in the next exercise plan,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, characterized in that the information management means manages the user's account information, training history, and feedback history, and generates positive coaching messages based on the user's emotional state.

[0897] (Claim 3)

[0898] The system according to claim 1, characterized in that the analysis means analyzes the user's behavior patterns using a structure detection algorithm, and the emotion analysis means analyzes the user's facial expression data.

[0899] "Application example 2 when combining with an emotional engine"

[0900] (Claim 1)

[0901] A computing device that receives user information and generates an individualized training plan,

[0902] An analysis device that receives a real-time video data stream from a terminal and performs video analysis,

[0903] A feedback generation device that generates feedback regarding the user's behavior based on the analysis results and transmits it to the terminal,

[0904] An information management device that saves the user's training history information and reflects it in the next training plan,

[0905] An emotion analysis device that detects the user's emotional state and adaptively adjusts the training content accordingly,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, characterized in that an information management device manages user identification information, training history information, and feedback history information, and an emotion analysis device analyzes the user's emotions and reflects them in the feedback.

[0909] (Claim 3)

[0910] The system according to claim 1, characterized in that the analysis device analyzes the user's movement patterns using a skeletal detection algorithm and further analyzes the user's facial expression data using an emotion analysis algorithm. [Explanation of Symbols]

[0911] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A computation means that receives user information and generates an individualized training plan, An analysis means that receives a real-time video stream from a terminal and performs video analysis, A feedback generation means generates feedback regarding the user's action form based on the analysis results and sends it to the terminal, A data management system that saves the user's training history and reflects it in the next training plan, A system that includes this.

2. The system according to claim 1, characterized in that the data management means manages user account information, training history, and feedback history.

3. The system according to claim 1, characterized in that the analysis means analyzes the user's movement form using a skeletal detection algorithm.

Images